Matches in SemOpenAlex for { <https://semopenalex.org/work/W4285181777> ?p ?o ?g. }
- W4285181777 endingPage "1229" @default.
- W4285181777 startingPage "1211" @default.
- W4285181777 abstract "Topic modeling on tweets is known to experience under-specificity and data sparsity due to its character limitation. In earlier studies, researchers attempted to address this problem by either 1) tweet aggregation, where related tweets are combined into a single document or 2) tweet expansion with related text from external sources. The first approach faces the problem of losing the topic distribution in individual tweets. While finding a relevant text from the external source for a random tweet in the second approach is challenging for various reasons like differences in writing styles, multilingual content, and informal text. In contrast to adding context from external resources or combining related tweets into a pool, this study uses the internal vocabulary (hashtags) to counter under-specificity and sparsity in tweets. Earlier studies have indicated hashtags to be an important feature for representing the underlying context present in the tweet. Sequential models like Bi-directional Long Short Term Memory (BiLSTM) and Convolution Neural Network (CNN) over distributed representation of words have shown promising results in capturing semantic relationships between words of a tweet in the past. Motivated by the above, this article proposes a unified framework of hashtag-based tweet expansion exploiting text-based and network-based representation learning methods such as BiLSTM, BERT, and Graph Convolution Network (GCN). The hashtag-based expanded tweets using the proposed framework have significantly improved topic modeling performance compared to un-expanded (raw) tweets and hashtag-pooling-based approaches over two real-world tweet datasets of different nature. Furthermore, this article also studies the significance of hashtags in topic modeling performance by experimenting with different combination of word types such as hashtags, keywords, and user mentions." @default.
- W4285181777 created "2022-07-14" @default.
- W4285181777 creator A5016797117 @default.
- W4285181777 creator A5056117065 @default.
- W4285181777 creator A5064501274 @default.
- W4285181777 date "2023-06-01" @default.
- W4285181777 modified "2023-09-29" @default.
- W4285181777 title "Hashtag-Based Tweet Expansion for Improved Topic Modeling" @default.
- W4285181777 cites W134292135 @default.
- W4285181777 cites W1579815680 @default.
- W4285181777 cites W1683269307 @default.
- W4285181777 cites W1983496208 @default.
- W4285181777 cites W2001082470 @default.
- W4285181777 cites W2004192095 @default.
- W4285181777 cites W2018268077 @default.
- W4285181777 cites W2031237011 @default.
- W4285181777 cites W2048195127 @default.
- W4285181777 cites W2063904635 @default.
- W4285181777 cites W2067084957 @default.
- W4285181777 cites W2084204081 @default.
- W4285181777 cites W2086038979 @default.
- W4285181777 cites W2089923519 @default.
- W4285181777 cites W2110324082 @default.
- W4285181777 cites W2111032703 @default.
- W4285181777 cites W2113984132 @default.
- W4285181777 cites W2147194983 @default.
- W4285181777 cites W2167232041 @default.
- W4285181777 cites W2168332560 @default.
- W4285181777 cites W2174706414 @default.
- W4285181777 cites W2247903663 @default.
- W4285181777 cites W2259851978 @default.
- W4285181777 cites W2277088878 @default.
- W4285181777 cites W2296388605 @default.
- W4285181777 cites W2299805819 @default.
- W4285181777 cites W2304191168 @default.
- W4285181777 cites W2324417593 @default.
- W4285181777 cites W2416353094 @default.
- W4285181777 cites W2554704889 @default.
- W4285181777 cites W2557383871 @default.
- W4285181777 cites W2577673625 @default.
- W4285181777 cites W2585577269 @default.
- W4285181777 cites W2585771002 @default.
- W4285181777 cites W2591922431 @default.
- W4285181777 cites W2594755990 @default.
- W4285181777 cites W2609608200 @default.
- W4285181777 cites W2750981579 @default.
- W4285181777 cites W2777671395 @default.
- W4285181777 cites W2783409278 @default.
- W4285181777 cites W2788919350 @default.
- W4285181777 cites W2798683079 @default.
- W4285181777 cites W2841110526 @default.
- W4285181777 cites W2944796298 @default.
- W4285181777 cites W2958550837 @default.
- W4285181777 cites W2968805944 @default.
- W4285181777 cites W2974043497 @default.
- W4285181777 cites W2978878685 @default.
- W4285181777 cites W3003447952 @default.
- W4285181777 cites W3016994297 @default.
- W4285181777 cites W3038967525 @default.
- W4285181777 cites W3043148752 @default.
- W4285181777 cites W3045464143 @default.
- W4285181777 cites W3101913037 @default.
- W4285181777 cites W3124914435 @default.
- W4285181777 cites W4239647775 @default.
- W4285181777 cites W746911252 @default.
- W4285181777 doi "https://doi.org/10.1109/tcss.2022.3171206" @default.
- W4285181777 hasPublicationYear "2023" @default.
- W4285181777 type Work @default.
- W4285181777 citedByCount "0" @default.
- W4285181777 crossrefType "journal-article" @default.
- W4285181777 hasAuthorship W4285181777A5016797117 @default.
- W4285181777 hasAuthorship W4285181777A5056117065 @default.
- W4285181777 hasAuthorship W4285181777A5064501274 @default.
- W4285181777 hasConcept C132525143 @default.
- W4285181777 hasConcept C138885662 @default.
- W4285181777 hasConcept C151730666 @default.
- W4285181777 hasConcept C154945302 @default.
- W4285181777 hasConcept C171686336 @default.
- W4285181777 hasConcept C17744445 @default.
- W4285181777 hasConcept C199539241 @default.
- W4285181777 hasConcept C204321447 @default.
- W4285181777 hasConcept C23123220 @default.
- W4285181777 hasConcept C2776359362 @default.
- W4285181777 hasConcept C2776401178 @default.
- W4285181777 hasConcept C2777601683 @default.
- W4285181777 hasConcept C2779343474 @default.
- W4285181777 hasConcept C2993807640 @default.
- W4285181777 hasConcept C41008148 @default.
- W4285181777 hasConcept C41895202 @default.
- W4285181777 hasConcept C70437156 @default.
- W4285181777 hasConcept C80444323 @default.
- W4285181777 hasConcept C81363708 @default.
- W4285181777 hasConcept C86803240 @default.
- W4285181777 hasConcept C90805587 @default.
- W4285181777 hasConcept C94625758 @default.
- W4285181777 hasConceptScore W4285181777C132525143 @default.
- W4285181777 hasConceptScore W4285181777C138885662 @default.
- W4285181777 hasConceptScore W4285181777C151730666 @default.